1 Commits

Author SHA1 Message Date
pengxiao 6395ee3b49 feat: replace pymupdf image extraction with pdf2image + Heron layout detection
PDF image extraction now renders pages with pdf2image, detects figure
regions using docling-layout-heron (RT-DETRv2), and crops only the
detected pictures. Removes full-page fallback for text-only pages.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-02 22:38:31 +08:00